Mouse Ileum Analysis

1 MERFISH Image visualization

This dataset [1] is downloaded from https://zenodo.org/record/5512749#.Yd3H0dHMKUl. The Baysor Cell segmentation and the author generated cell type assignment are used in the analysis.

1.1 Plot Cell by centroid Coordinates

Spacial.information=read.csv('segmentation.csv.gz',header = T)

Spacial.information=Spacial.information[Spacial.information$is_noise!='true',]
Spacial.information$cell=as.character(Spacial.information$cell)
Cell_spacial_information=read.csv('segmentation_cell_stats.csv.gz',header = T,row.names = 1)

Celltype=read.csv('cell_assignment.csv.gz',header = T,row.names = 1)
colnames(Celltype)=c('Celltype')

Cell_spacial_information=merge(Cell_spacial_information,Celltype,by = 0)
colnames(Cell_spacial_information)=paste0('cell_',colnames(Cell_spacial_information))

colnames(Cell_spacial_information)[1]='cell'

Cell_spacial_information=Cell_spacial_information[Cell_spacial_information$cell_Celltype!='Removed',]
getPalette = colorRampPalette(brewer.pal(9, "Dark2"))

## Warning in brewer.pal(9, "Dark2"): n too large, allowed maximum for palette Dark2 is 8
## Returning the palette you asked for with that many colors

color=getPalette(length(unique(Cell_spacial_information$cell_Celltype)))

ggplot(Cell_spacial_information,aes(x=cell_x,y=cell_y,colour=cell_Celltype))+geom_point()+
  xlim(min(Cell_spacial_information$cell_x),max(Cell_spacial_information$cell_x))+
  ylim(min(Cell_spacial_information$cell_y),max(Cell_spacial_information$cell_y)) + scale_color_manual(values = color)+ theme_bw() + 
  theme(
    # get rid of panel grids
    panel.grid.major = element_blank(),
    panel.grid.minor = element_blank(),
    # Change plot and panel background
    plot.background=element_rect(fill = "black"),
    panel.background = element_rect(fill = 'black'),
    # Change legend 
    #legend.position = c(0.6, 0.07),
    #legend.direction = "horizontal",
    legend.background = element_rect(fill = "black", color = NA),
    legend.key = element_rect(color = "gray", fill = "black"),
    legend.title = element_text(color = "white"),
    legend.text = element_text(color = "white")
  )

1.2 Plot Cell by real probes.

Spacial.information=Spacial.information[Spacial.information$cell%in%rownames(Cell_spacial_information),]

Spacial.information=merge(Spacial.information,Cell_spacial_information,by = 'cell')

colnames(Spacial.information)[grepl('Celltype',colnames(Spacial.information))]='Celltype'


ggplot(Spacial.information,aes(x=x,y=y,colour=Celltype))+geom_point(shape='.')+
  xlim(min(Spacial.information$x),max(Spacial.information$x))+
  ylim(min(Spacial.information$y),max(Spacial.information$y)) + scale_color_manual(values = color)+ theme_bw() + 
  theme(
    # get rid of panel grids
    panel.grid.major = element_blank(),
    panel.grid.minor = element_blank(),
    # Change plot and panel background
    plot.background=element_rect(fill = "black"),
    panel.background = element_rect(fill = 'black'),
    # Change legend 
    #legend.position = c(0.6, 0.07),
    #legend.direction = "horizontal",
    legend.background = element_rect(fill = "black", color = NA),
    legend.key = element_rect(color = "gray", fill = "black"),
    legend.title = element_text(color = "white"),
    legend.text = element_text(color = "white")
  )

2 Analysis

By looking at the visualization results from Part 1, we can see that the cellular composition of different parts of the tissue are different.

Can we use the unsupervised clustering algorithm to find different parts of the tissue?

Time to find out.

2.1 Area Calculator Function

This function will break the Image into multiple small fragments. and calculate the cell composition in each small fragments.

Logic:
  The whole image is broken into small fragments.

  for each small fragment:

    for each cell has overlap with the small fragment:
  
      if the cell has more than x% (x determined by the user) of cell's probes'areas in the small fragment, the cell is determined to be in the small fragment.
    Cell composition of the small fragment is determined by the cells assigned to it.
  

The percentage threshold and the size of small fragment can be determined by the user.

One tip: if the number of fragments is increased, please decrease the proportion_threshold. Otherwise many area will be deemed as no cells.

source('functions.R')

Area_Calculated_from_Probe=Area_Calculator(min(Spacial.information$x),
                                 max(Spacial.information$x),
                                 min(Spacial.information$y),
                                 max(Spacial.information$y),
                                 50,Spacial.information,proportion_threshold = 0.5)

cell_coodinates=data.frame(x=Cell_spacial_information$cell_x,y=Cell_spacial_information$cell_y,cell=Cell_spacial_information$cell,
                           Celltype=Cell_spacial_information$cell_Celltype)
Area_Calculated_from_Coordinates=Area_Counter(min(cell_coodinates$x),
                                 max(cell_coodinates$x),
                                 min(cell_coodinates$y),
                                 max(cell_coodinates$y),
                                 50,cell_coodinates)

2.2 Clustering

In this case I used the Leiden Community detection Algorithm from igraph package to cluster the area.

ClusterfromProbe_results <- Area_Cluster(Area_Calculated_from_Probe
                                         ,ScaleFactor = 1e6,resolution_parameter = 0.5)

## Building SNN based on a provided distance matrix

## Computing SNN

ClusterfromCoordinates_results <- Area_Cluster(Area_Calculated_from_Coordinates,ScaleFactor = 1e6,resolution_parameter = 0.5)

## Building SNN based on a provided distance matrix
## Computing SNN

2.2.1 Visualization of Clustering Results from Probe

Area.Cluster.assignment=ClusterfromProbe_results$Area.Cluster.assignment

Clustering.Distribution=ClusterfromProbe_results$Clustering.Distribution

melt=Area.Cluster.assignment
melt$cluster=as.factor(melt$cluster)
melt=melt(melt,id.vars='cluster')
colnames(melt)=c('Cluster','CellType','Cells')
Cluster_cell_composition=ggplot(melt,aes(x=Cells,y=Cluster,fill=CellType))+geom_bar(stat = 'identity',position = 'fill')+ scale_fill_manual(values = color)+ theme_bw()

centroid.graph=ggplot(Cell_spacial_information,aes(x=cell_x,y=cell_y,colour=cell_Celltype))+geom_point()+
  xlim(min(Cell_spacial_information$cell_x),max(Cell_spacial_information$cell_x))+
  ylim(min(Cell_spacial_information$cell_y),max(Cell_spacial_information$cell_y)) + scale_color_manual(values = color)+ theme_bw() +xlab('x') +ylab('y') +
  theme(legend.position = "none",
    # get rid of panel grids
    panel.grid.major = element_blank(),
    panel.grid.minor = element_blank(),
    # Change plot and panel background
    # Change legend 
    #legend.position = c(0.6, 0.07),
    #legend.direction = "horizontal",
)
Clustering.Distribution.plot=ClusterfromProbe_results$Clustering.Distribution.plot

grid.arrange(Clustering.Distribution.plot, centroid.graph,Cluster_cell_composition, ncol=2)

Clustering.Distribution.plot

centroid.graph

Cluster_cell_composition

2.2.2 Visualization of Clustering Results from Coordinates

Area.Cluster.assignment=ClusterfromCoordinates_results$Area.Cluster.assignment

Clustering.Distribution=ClusterfromCoordinates_results$Clustering.Distribution

melt=Area.Cluster.assignment
melt$cluster=as.factor(melt$cluster)
melt=melt(melt,id.vars='cluster')
colnames(melt)=c('Cluster','CellType','Cells')
Cluster_cell_composition=ggplot(melt,aes(x=Cells,y=Cluster,fill=CellType))+geom_bar(stat = 'identity',position = 'fill')+ scale_fill_manual(values = color)+ theme_bw()

centroid.graph=ggplot(Cell_spacial_information,aes(x=cell_x,y=cell_y,colour=cell_Celltype))+geom_point()+
  xlim(min(Cell_spacial_information$cell_x),max(Cell_spacial_information$cell_x))+
  ylim(min(Cell_spacial_information$cell_y),max(Cell_spacial_information$cell_y)) + scale_color_manual(values = color)+ theme_bw() +xlab('x') +ylab('y') +
  theme(legend.position = "none",
    # get rid of panel grids
    panel.grid.major = element_blank(),
    panel.grid.minor = element_blank(),
    # Change plot and panel background
    # Change legend 
    #legend.position = c(0.6, 0.07),
    #legend.direction = "horizontal",
)
Clustering.Distribution.plot=ClusterfromCoordinates_results$Clustering.Distribution.plot

grid.arrange(Clustering.Distribution.plot, centroid.graph,Cluster_cell_composition, ncol=2)

Clustering.Distribution.plot

centroid.graph

Cluster_cell_composition

3 Conclusion

Coming soon.

4 Reference

[1] Moffitt, Jeffrey, Xu, Rosalind, Kharchenko, Peter, Petukhov, Viktor, Cadinu, Paolo, Soldatov, Ruslan, & Khodosevich, Konstantin. (2021). MERFISH measurements in the mouse ileum [Data set]. https://doi.org/10.5061/dryad.jm63xsjb2